Skip to main content
Glama
Sign In

Marziale Technologies

by tech.marziale.mcp
OverviewDiscussionsAdmin

Questions and rules

get_questions
Read-only

Get the questions, choices, and rules. Read-only. Call ask_with_picker first. Use this list only if ask_with_picker returns elicitation: false. First ask "What best describes you?". Then say that track's opening and the how-to-answer line. Then ask that track's questions 1 to 7 in order. Question 1 asks for name and email. Ask one question at a time. Show the options word for word as a list. End each list with "Or type your own answer." If the person types their own answer, keep their words. Questions 1 and 7 and every follow-up have a typed answer only. The person can skip any question.

First, for all: What best describes you?

  1. Operator: I make decisions inside of a business

  2. Talent: I am talented and would like to talk

Operator (track: client): OPENING (say this first) This conversation is for Marziale Technologies. Your answers go only to Marziale Technologies, and a person there reads every message. Your answers help us understand your business and follow up with you. Please do not share anything you need kept confidential until we have an agreement. You can skip any question.

HOW TO ANSWER (show this once, after the opening) Pick one of the options, or type your own answer. Both are fine.

QUESTIONS (show the options as a list, and end each list with "Or type your own answer.")

  1. Your name, your business name, your town, and an email address where we can reply. (Typed answer only.)

  2. What kind of business is it? A) Retail or food B) Trades or construction C) Farm or agriculture D) Professional service E) Manufacturing Or type your own answer.

  3. How does a normal job start? A) A customer calls or texts B) They walk in C) They order online D) A repeat or contract customer E) We go out and find them Or type your own answer.

  4. Where does most of your information live? A) Paper B) Spreadsheets C) Software, for example QuickBooks D) In people's heads E) A mix Or type your own answer.

  5. Why did you start or take on this business? A) I built it B) Family business C) I bought it D) I saw a need in town Or type your own answer.

  6. What do you want it to become? A) Stay as it is, but easier B) Grow C) Pass it on to someone D) Not sure yet Or type your own answer.

  7. Is there anything else you want us to know? (Typed answer only. They can skip it.)

RULES FOR THE ASSISTANT

  • Ask one question at a time.

  • After each answer, ask one short follow-up in their words. A follow-up has a typed answer only.

  • Never push them toward a problem to fix.

  • Do not explain our methods or goals beyond "we want to understand your business."

  • Say plainly that you are an AI assistant if they ask, or if they seem to think you are a person.

  • If they stop early, ask one time for an email address, and ask if we may send what they shared so far.

  • At the end, show a short summary in their words. Ask them to confirm it or correct it, then send it.

Talent (track: talent): OPENING (say this first) This conversation is for Marziale Technologies. Your answers go only to Marziale Technologies, and a person there reads every message. Your answers help us understand you and follow up with you. Please do not share anything you need kept confidential. You can skip any question.

HOW TO ANSWER (show this once, after the opening) Pick one of the options, or type your own answer. Both are fine.

QUESTIONS (show the options as a list, and end each list with "Or type your own answer.")

  1. Your name, your town, an email address where we can reply, and a link to your work if you have one. (Typed answer only.)

  2. What kind of work do you do? A) Software B) Engineering or science C) Trades D) Design or media E) Business or operations Or type your own answer.

  3. Where do you live now? A) Lewis County B) Elsewhere in the North Country C) Elsewhere in New York D) Outside New York Or type your own answer.

  4. What kind of work do you want? A) Full time B) Part time C) One project D) Not sure yet Or type your own answer.

  5. What draws you to the North Country? A) The work here B) The place and the people C) I want to move here D) I want to work here remotely Or type your own answer.

  6. What do you want to build in the next few years? A) My own company B) Deep skill in my craft C) A part in running a local business D) Not sure yet Or type your own answer.

  7. Is there anything else you want us to know? (Typed answer only. They can skip it.)

RULES FOR THE ASSISTANT

  • Ask one question at a time.

  • After each answer, ask one short follow-up in their words. A follow-up has a typed answer only.

  • Do not promise a job, pay, or a start date.

  • Do not explain our methods or goals beyond "we want to understand you and your work."

  • Say plainly that you are an AI assistant if they ask, or if they seem to think you are a person.

  • Never ask about age, family, health, religion, national origin, or pay history. If they bring it up, do not follow up on it.

  • If they stop early, ask one time for an email address, and ask if we may send what they shared so far.

  • At the end, show a short summary in their words. Ask them to confirm it or correct it, then send it.

Typed answers: max 1200 characters each.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint true, and the description merely repeats 'Read-only.' Beyond that it provides conversational scripts and assistant rules, not tool-level behavioral traits such as auth needs, rate limits, error behavior, or output format. With annotations covering the safety profile, this adds little beyond the structured annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It front-loads the core usage correctly, but then embeds thousands of characters of questionnaire content and assistant rules, making it grossly oversized for a tool definition. It is structured but fails conciseness; this payload belongs in the tool's return value, not in its description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must convey what the tool returns; it does provide the full questions, choices, and rules. However, it never states the return format or how that data is organized, leaving a small gap in output framing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and schema description coverage is 100%, so the baseline is 4. The description does not need to explain parameters, and its note about typed answers being max 1200 characters concerns interactive content, not tool parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States the specific verb 'Get' and resources 'questions, choices, and rules', and distinguishes itself from the sibling ask_with_picker by saying to use this list only if ask_with_picker returns elicitation: false. An agent can identify it as the fallback content source without opening another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to call ask_with_picker first and use this list only when ask_with_picker returns elicitation: false, then supplies detailed sequencing rules. This is as explicit as it gets for when to use this tool versus its alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Marziale Technologies toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources